synthesis-fact-checking

synthesis-fact-checking is a skill for Claude Code, Codex from synthesisengineering/synthesis-skills. It costs 117 tokens per session (7,566 once invoked), scanned A, original, Apache-2.0.

A repeatable process for checking whether articles, news, blog posts, and AI-generated material are factually correct before publication. It covers source checking, attribution, quotations, paraphrases, links, and AI-created sources.

In plain words
What is it for?
It helps verify statements, quotations, citations, translated material, source links, and claims assembled from multiple references.
Why use it?
It helps catch claims that became distorted, unsupported, duplicated from unreliable material, or attached to the wrong source.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: positional $N argument.

Part of the synthesis-skills plugin — 63 skills, 4 hooks shipped together

Good fit It helps verify statements, quotations, citations, translated material, source links, and claims assembled from multiple references.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/synthesisengineering/synthesis-skills/synthesis-fact-checking
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add synthesisengineering/synthesis-skills --skill synthesis-fact-checking
Clone the repo
git clone --depth 1 https://github.com/synthesisengineering/synthesis-skills

Made for: Claude Code, Codex.

Or install synthesis-skills, the plugin that ships this one along with the rest of its 63 skills, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for synthesis-fact-checking

README.md
[![agentmods](https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-fact-checking/github.svg)](https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-fact-checking)
Your own site
<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-fact-checking"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-fact-checking/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for synthesis-fact-checking

Your own site · 80×15
<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-fact-checking"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-fact-checking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,566 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 455
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00117 $0.07566
Opus 5 $0.00059 $0.03783
Sonnet 5 $0.00023 $0.01513
Haiku 4.5 $0.00012 $0.00757

Measured 9d ago against content hash 2003b3aff293, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

synthesis-fact-checking scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/synthesis-fact-checking/SKILL.md · 508 lines

How it starts

The opening of the file, as written. The whole thing — 508 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fact-Check Process for Articles and AI-Synthesized Content

Purpose

This skill provides a repeatable process for verifying factual accuracy of articles, blog posts, and news content before publication. v2.0 is specifically calibrated for the recursive-contamination problem: AI-generated text now constitutes a plurality of newly indexed English-language web pages (per Ahrefs measurement of newly indexed pages in April 2025), which means AI outputs become source material for the next generation of AI outputs and human research. Multi-source confidence requires graph independence, not raw count.

The companion skill, synthesis-content-quality, addresses stylistic and substantive quality. This skill addresses factual correctness.

What v2.0 adds

  • Nine new protocol sections (C1) for the structural gaps in v1.1.0: nested attribution, paraphrase boundary drift, composite quotes, position-shifting, source-translation drift, URL rot vs hallucination, AI-generated synthetic sources, citation laundering chains, tool-specific hallucination patterns. Full detail in references/detailed-protocols.md.
  • Per-family hallucination signatures. Claude over-produces plausible-seeming DOIs; GPT invents URLs on real domains; Gemini drifts to vague "studies show"; DeepSeek language-mixes under reasoning; Llama fabricates above approximately 32K context per RIKER benchmark; Grok fabricates X/Twitter quotes. Family-conditional detection is the bucket-C parallel to bucket-A's family-conditional stylistic detection. Full detail in references/per-family-hallucination-signatures.md.
  • Graph-independence revision to section 2 (Multi-Source Confidence Framework). Citation laundering chains collapse cross-source corroboration to a single AI-generated upstream. Confidence conditions on graph independence, not on raw count. Full detail in references/citation-laundering-detection.md.
  • Section 4 refresh. Updated examples from 2025-2026 production incidents: Mostafavi sanction ($10,000), Goldberg Segalla sanction ($59,500 total), Chicago Sun-Times summer reading list, Springer "Mastering ML" book retraction, BBC/EBU 45 percent significant-issues rate, Topaz et al. May 2026 Lancet letter (1 in 277 PubMed papers referencing fabricated paper, twelvefold rise from 2023), Damien Charlotin's database of 1,455+ sanctioned legal cases, Mata v. Avianca, Stanford RegLab Magesh measurement (17 to 33 percent legal-AI hallucination rate). Full incident archive in references/production-incident-archive.md.
  • Section 4f demote. Hallucinated citations as a single bucket is demoted. The failure mode splits into the C1-URLROT-001 / C1-SYNTH-001 / C1-LAUNDER-001 trio plus residual pure-fabrication.

Read the full file on GitHub · 508 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 508 lines · 117 tokens per session scan A 2003b3aff293

Subscribe to this mod's changes

synthesis-fact-checking is a skill published in the GitHub repository synthesisengineering/synthesis-skills (18 stars, last pushed 2d ago), licensed Apache-2.0. It adds 117 tokens to every session and 7,566 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens